Learning Rare Behaviours

12 years 28 days ago
Learning Rare Behaviours
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We treat this as a weakly supervised classification problem and propose a novel topic model: Multi-Class Delta Latent Dirichlet Allocation which learns to model rare behaviours from a few weakly labelled videos as well as typical behaviours from uninteresting videos by collaboratively sharing features among all classes of footage. The learned model is able to accurately classify unseen data. We further explore a novel method for detecting unknown rare behaviours in unseen data by synthesising new plausible topics to hypothesise any potential behavioural conflicts. Extensive validation using both simulated and real-world CCTV video data demonstrates the superior performance of the proposed framework compared to conventional unsupervised detection and supervised classification approaches.
Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao
Added 12 May 2011
Updated 22 Jun 2011
Type Journal
Year 2010
Where ACCV
Authors Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao Xiang
Comments (0)